Service Response Time

We combine these models to predict average total response time R for the service, deliberately ignoring congestion on the network paths to the clients (which the utility OS cannot control). Given a measure D_P of average per-request service demand on the Web server CPU, CPU response time R_P is given by a simple queuing model similar to the storage model above; previous work [12] illustrates use of such a model to adaptively provision CPU resources for Web services. The service's average response time R is simply:

R = R_P + R_S (1 - H) (5)

This ignores the CPU cost of I/O and the effects of prefetching for large files. The CPU and storage models already account (crudely) for these factors in the average case.